CircleCI Automation via Rube MCP
Automate CircleCI CI/CD operations through Composio's CircleCI toolkit via Rube MCP.
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active CircleCI connection via
RUBE_MANAGE_CONNECTIONS with toolkit circleci
- Always call
RUBE_SEARCH_TOOLS first to get current tool schemas
Setup
Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
- Verify Rube MCP is available by confirming
RUBE_SEARCH_TOOLS responds
- Call
RUBE_MANAGE_CONNECTIONS with toolkit circleci
- If connection is not ACTIVE, follow the returned auth link to complete CircleCI authentication
- Confirm connection status shows ACTIVE before running any workflows
Core Workflows
1. Trigger a Pipeline
When to use: User wants to start a new CI/CD pipeline run
Tool sequence:
CIRCLECI_TRIGGER_PIPELINE - Trigger a new pipeline on a project [Required]
CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID - Monitor resulting workflows [Optional]
Key parameters:
project_slug: Project identifier in format gh/org/repo or bb/org/repo
branch: Git branch to run the pipeline on
tag: Git tag to run the pipeline on (mutually exclusive with branch)
parameters: Pipeline parameter key-value pairs
Pitfalls:
project_slug format is {vcs}/{org}/{repo} (e.g., gh/myorg/myrepo)
branch and tag are mutually exclusive; providing both causes an error
- Pipeline parameters must match those defined in
.circleci/config.yml
- Triggering returns a pipeline ID; workflows start asynchronously
2. Monitor Pipelines and Workflows
When to use: User wants to check the status of pipelines or workflows
Tool sequence:
CIRCLECI_LIST_PIPELINES_FOR_PROJECT - List recent pipelines for a project [Required]
CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID - List workflows within a pipeline [Required]
CIRCLECI_GET_PIPELINE_CONFIG - View the pipeline configuration used [Optional]
Key parameters:
project_slug: Project identifier in {vcs}/{org}/{repo} format
pipeline_id: UUID of a specific pipeline
branch: Filter pipelines by branch name
page_token: Pagination cursor for next page of results
Pitfalls:
- Pipeline IDs are UUIDs, not numeric IDs
- Workflows inherit the pipeline ID; a single pipeline can have multiple workflows
- Workflow states include: success, running, not_run, failed, error, failing, on_hold, canceled, unauthorized
page_token is returned in responses for pagination; continue until absent
3. Inspect Job Details
When to use: User wants to drill into a specific job's execution details
Tool sequence:
CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID - Find workflow containing the job [Prerequisite]
CIRCLECI_GET_JOB_DETAILS - Get detailed job information [Required]
Key parameters:
project_slug: Project identifier
job_number: Numeric job number (not UUID)
Pitfalls:
- Job numbers are integers, not UUIDs (unlike pipeline and workflow IDs)
- Job details include executor type, parallelism, start/stop times, and status
- Job statuses: success, running, not_run, failed, retried, timedout, infrastructure_fail, canceled
4. Retrieve Build Artifacts
When to use: User wants to download or list artifacts produced by a job
Tool sequence:
CIRCLECI_GET_JOB_DETAILS - Confirm job completed successfully [Prerequisite]
CIRCLECI_GET_JOB_ARTIFACTS - List all artifacts from the job [Required]
Key parameters:
project_slug: Project identifier
job_number: Numeric job number
Pitfalls:
- Artifacts are only available after job completion
- Each artifact has a
path and url for download
- Artifact URLs may require authentication headers to download
- Large artifacts may have download size limits
5. Review Test Results
When to use: User wants to check test outcomes for a specific job
Tool sequence:
CIRCLECI_GET_JOB_DETAILS - Verify job ran tests [Prerequisite]
CIRCLECI_GET_TEST_METADATA - Retrieve test results and metadata [Required]
Key parameters:
project_slug: Project identifier
job_number: Numeric job number
Pitfalls:
- Test metadata requires the job to have uploaded test results (JUnit XML format)
- If no test results were uploaded, the response will be empty
- Test metadata includes classname, name, result, message, and run_time fields
- Failed tests include failure messages in the
message field
Common Patterns
Project Slug Format
Format: {vcs_type}/{org_name}/{repo_name}
- GitHub: gh/myorg/myrepo
- Bitbucket: bb/myorg/myrepo
Pipeline -> Workflow -> Job Hierarchy
1. Call CIRCLECI_LIST_PIPELINES_FOR_PROJECT to get pipeline IDs
2. Call CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID with pipeline_id
3. Extract job numbers from workflow details
4. Call CIRCLECI_GET_JOB_DETAILS with job_number
Pagination
- Check response for
next_page_token field
- Pass token as
page_token in next request
- Continue until
next_page_token is absent or null
Known Pitfalls
ID Formats:
- Pipeline IDs: UUIDs (e.g.,
5034460f-c7c4-4c43-9457-de07e2029e7b)
- Workflow IDs: UUIDs
- Job numbers: Integers (e.g.,
123)
- Do NOT mix up UUIDs and integers between different endpoints
Project Slugs:
- Must include VCS prefix:
gh/ for GitHub, bb/ for Bitbucket
- Organization and repo names are case-sensitive
- Incorrect slug format causes 404 errors
Rate Limits:
- CircleCI API has per-endpoint rate limits
- Implement exponential backoff on 429 responses
- Avoid rapid polling; use reasonable intervals (5-10 seconds)
Quick Reference
| Task |
Tool Slug |
Key Params |
| Trigger pipeline |
CIRCLECI_TRIGGER_PIPELINE |
project_slug, branch, parameters |
| List pipelines |
CIRCLECI_LIST_PIPELINES_FOR_PROJECT |
project_slug, branch |
| List workflows |
CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID |
pipeline_id |
| Get pipeline config |
CIRCLECI_GET_PIPELINE_CONFIG |
pipeline_id |
| Get job details |
CIRCLECI_GET_JOB_DETAILS |
project_slug, job_number |
| Get job artifacts |
CIRCLECI_GET_JOB_ARTIFACTS |
project_slug, job_number |
| Get test metadata |
CIRCLECI_GET_TEST_METADATA |
project_slug, job_number |
When to Use
This skill is applicable to execute the workflow or actions described in the overview.
Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Source: sickn33/agentic-awesome-skills → skills/circleci-automation/SKILL.md
Also appears in: sickn33/agentic-awesome-skills/plugins/agentic-awesome-skills/skills/circleci-automation/SKILL.md, sickn33/agentic-awesome-skills/plugins/agentic-awesome-skills-claude/skills/circleci-automation/SKILL.md
1---2name: circleci-automation3description: Automate CircleCI tasks via Rube MCP (Composio): trigger pipelines, monitor workflows/jobs, retrieve artifacts and test metadata. Always search tools first for current schemas.4---567# CircleCI Automation via Rube MCP89Automate CircleCI CI/CD operations through Composio's CircleCI toolkit via Rube MCP.1011## Prerequisites1213- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)14- Active CircleCI connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `circleci`15- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas1617## Setup1819**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.2021221. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds232. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `circleci`243. If connection is not ACTIVE, follow the returned auth link to complete CircleCI authentication254. Confirm connection status shows ACTIVE before running any workflows2627## Core Workflows2829### 1. Trigger a Pipeline3031**When to use**: User wants to start a new CI/CD pipeline run3233**Tool sequence**:341. `CIRCLECI_TRIGGER_PIPELINE` - Trigger a new pipeline on a project [Required]352. `CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID` - Monitor resulting workflows [Optional]3637**Key parameters**:38- `project_slug`: Project identifier in format `gh/org/repo` or `bb/org/repo`39- `branch`: Git branch to run the pipeline on40- `tag`: Git tag to run the pipeline on (mutually exclusive with branch)41- `parameters`: Pipeline parameter key-value pairs4243**Pitfalls**:44- `project_slug` format is `{vcs}/{org}/{repo}` (e.g., `gh/myorg/myrepo`)45- `branch` and `tag` are mutually exclusive; providing both causes an error46- Pipeline parameters must match those defined in `.circleci/config.yml`47- Triggering returns a pipeline ID; workflows start asynchronously4849### 2. Monitor Pipelines and Workflows5051**When to use**: User wants to check the status of pipelines or workflows5253**Tool sequence**:541. `CIRCLECI_LIST_PIPELINES_FOR_PROJECT` - List recent pipelines for a project [Required]552. `CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID` - List workflows within a pipeline [Required]563. `CIRCLECI_GET_PIPELINE_CONFIG` - View the pipeline configuration used [Optional]5758**Key parameters**:59- `project_slug`: Project identifier in `{vcs}/{org}/{repo}` format60- `pipeline_id`: UUID of a specific pipeline61- `branch`: Filter pipelines by branch name62- `page_token`: Pagination cursor for next page of results6364**Pitfalls**:65- Pipeline IDs are UUIDs, not numeric IDs66- Workflows inherit the pipeline ID; a single pipeline can have multiple workflows67- Workflow states include: success, running, not_run, failed, error, failing, on_hold, canceled, unauthorized68- `page_token` is returned in responses for pagination; continue until absent6970### 3. Inspect Job Details7172**When to use**: User wants to drill into a specific job's execution details7374**Tool sequence**:751. `CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID` - Find workflow containing the job [Prerequisite]762. `CIRCLECI_GET_JOB_DETAILS` - Get detailed job information [Required]7778**Key parameters**:79- `project_slug`: Project identifier80- `job_number`: Numeric job number (not UUID)8182**Pitfalls**:83- Job numbers are integers, not UUIDs (unlike pipeline and workflow IDs)84- Job details include executor type, parallelism, start/stop times, and status85- Job statuses: success, running, not_run, failed, retried, timedout, infrastructure_fail, canceled8687### 4. Retrieve Build Artifacts8889**When to use**: User wants to download or list artifacts produced by a job9091**Tool sequence**:921. `CIRCLECI_GET_JOB_DETAILS` - Confirm job completed successfully [Prerequisite]932. `CIRCLECI_GET_JOB_ARTIFACTS` - List all artifacts from the job [Required]9495**Key parameters**:96- `project_slug`: Project identifier97- `job_number`: Numeric job number9899**Pitfalls**:100- Artifacts are only available after job completion101- Each artifact has a `path` and `url` for download102- Artifact URLs may require authentication headers to download103- Large artifacts may have download size limits104105### 5. Review Test Results106107**When to use**: User wants to check test outcomes for a specific job108109**Tool sequence**:1101. `CIRCLECI_GET_JOB_DETAILS` - Verify job ran tests [Prerequisite]1112. `CIRCLECI_GET_TEST_METADATA` - Retrieve test results and metadata [Required]112113**Key parameters**:114- `project_slug`: Project identifier115- `job_number`: Numeric job number116117**Pitfalls**:118- Test metadata requires the job to have uploaded test results (JUnit XML format)119- If no test results were uploaded, the response will be empty120- Test metadata includes classname, name, result, message, and run_time fields121- Failed tests include failure messages in the `message` field122123## Common Patterns124125### Project Slug Format126127```128Format: {vcs_type}/{org_name}/{repo_name}129- GitHub: gh/myorg/myrepo130- Bitbucket: bb/myorg/myrepo131```132133### Pipeline -> Workflow -> Job Hierarchy134135```1361. Call CIRCLECI_LIST_PIPELINES_FOR_PROJECT to get pipeline IDs1372. Call CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID with pipeline_id1383. Extract job numbers from workflow details1394. Call CIRCLECI_GET_JOB_DETAILS with job_number140```141142### Pagination143144- Check response for `next_page_token` field145- Pass token as `page_token` in next request146- Continue until `next_page_token` is absent or null147148## Known Pitfalls149150**ID Formats**:151- Pipeline IDs: UUIDs (e.g., `5034460f-c7c4-4c43-9457-de07e2029e7b`)152- Workflow IDs: UUIDs153- Job numbers: Integers (e.g., `123`)154- Do NOT mix up UUIDs and integers between different endpoints155156**Project Slugs**:157- Must include VCS prefix: `gh/` for GitHub, `bb/` for Bitbucket158- Organization and repo names are case-sensitive159- Incorrect slug format causes 404 errors160161**Rate Limits**:162- CircleCI API has per-endpoint rate limits163- Implement exponential backoff on 429 responses164- Avoid rapid polling; use reasonable intervals (5-10 seconds)165166## Quick Reference167168| Task | Tool Slug | Key Params |169|------|-----------|------------|170| Trigger pipeline | CIRCLECI_TRIGGER_PIPELINE | project_slug, branch, parameters |171| List pipelines | CIRCLECI_LIST_PIPELINES_FOR_PROJECT | project_slug, branch |172| List workflows | CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID | pipeline_id |173| Get pipeline config | CIRCLECI_GET_PIPELINE_CONFIG | pipeline_id |174| Get job details | CIRCLECI_GET_JOB_DETAILS | project_slug, job_number |175| Get job artifacts | CIRCLECI_GET_JOB_ARTIFACTS | project_slug, job_number |176| Get test metadata | CIRCLECI_GET_TEST_METADATA | project_slug, job_number |177178## When to Use179This skill is applicable to execute the workflow or actions described in the overview.180181## Limitations182- Use this skill only when the task clearly matches the scope described above.183- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.184- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.185186---187188**Source:** [`sickn33/agentic-awesome-skills`](https://github.com/sickn33/agentic-awesome-skills) → `skills/circleci-automation/SKILL.md`189190**Also appears in:** `sickn33/agentic-awesome-skills/plugins/agentic-awesome-skills/skills/circleci-automation/SKILL.md`, `sickn33/agentic-awesome-skills/plugins/agentic-awesome-skills-claude/skills/circleci-automation/SKILL.md`